Shuming Liu
Shuming Liu is a Ph.D. student in the computer science program at the Image and Video Understanding Lab (IVUL), King Abdullah University of Science and Technology (KAUST), under the supervision of Professor Bernard Ghanem, where his research focuses on video understanding and multimodal large language models for efficient video reasoning and temporal video understanding.
Biography
Shuming Liu is a Ph.D. candidate in Computer Science at the GenAI Center of Excellence, King Abdullah University of Science and Technology (KAUST), advised by Prof. Bernard Ghanem. He received his master's degree from Shanghai Jiao Tong University.
He was a Research Scientist Intern with Qwen in 2026, working on long-horizon agentic multimodal reasoning for Qwen-VL models, and with Meta AI in 2025 and 2026, focusing on adaptive reasoning and on-policy self-distillation for video-language models.
He has published multiple papers at leading conferences, including CVPR, ECCV, and ICLR, and has won first place in several CVPR challenges.
Expertise and Interests
Shuming Liu's research focuses on video understanding and multimodal large language models, with recent work spanning adaptive video reasoning, efficient long-video modeling, and temporal video understanding.
Awards and Distinctions
- Dean's List Award, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), 2025
- Dean's List Award, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), 2024
Education
- Master of Science (M.S.)
- Computer Science, Shanghai Jiao Tong University (SJTU), China, 2021
- Bachelor of Science (B.S.)
- Computer Science, Xi'an Jiaotong University (XJTU), China, 2018